/// <inheritdoc/>
public object Clone()
{
var result = new NEATGenome();
result.Copy(this);
return(result);
}
/// <summary>
/// Construct a genome by copying another.
/// </summary>
/// <param name="other">The other genome.</param>
public NEATGenome(NEATGenome other)
{
NetworkDepth = other.NetworkDepth;
Population = other.Population;
Score = other.Score;
AdjustedScore = other.AdjustedScore;
InputCount = other.InputCount;
OutputCount = other.OutputCount;
Species = other.Species;
// copy neurons
foreach (NEATNeuronGene oldGene in other.NeuronsChromosome)
{
var newGene = new NEATNeuronGene(oldGene);
_neuronsList.Add(newGene);
}
// copy links
foreach (var oldGene in other.LinksChromosome)
{
var newGene = new NEATLinkGene(
oldGene.FromNeuronId, oldGene.ToNeuronId,
oldGene.Enabled, oldGene.InnovationId,
oldGene.Weight);
_linksList.Add(newGene);
}
}
/// <summary>
/// Construct a genome by copying another.
/// </summary>
/// <param name="other">The other genome.</param>
public NEATGenome(NEATGenome other)
{
NetworkDepth = other.NetworkDepth;
Population = other.Population;
Score = other.Score;
AdjustedScore = other.AdjustedScore;
InputCount = other.InputCount;
OutputCount = other.OutputCount;
Species = other.Species;
// copy neurons
foreach (NEATNeuronGene oldGene in other.NeuronsChromosome)
{
var newGene = new NEATNeuronGene(oldGene);
_neuronsList.Add(newGene);
}
// copy links
foreach (var oldGene in other.LinksChromosome)
{
var newGene = new NEATLinkGene(
oldGene.FromNeuronId, oldGene.ToNeuronId,
oldGene.Enabled, oldGene.InnovationId,
oldGene.Weight);
_linksList.Add(newGene);
}
}
public NEATGenome(NEATGenome other)
{
goto Label_0182;
Label_0017:
this.inputCount = other.inputCount;
this.outputCount = other.outputCount;
Label_002F:
this.speciesID = other.speciesID;
foreach (IGene gene in other.Neurons.Genes)
{
NEATNeuronGene gene2 = (NEATNeuronGene) gene;
if (0xff != 0)
{
NEATNeuronGene gene3 = new NEATNeuronGene(gene2.NeuronType, gene2.Id, gene2.SplitY, gene2.SplitX, gene2.Recurrent, gene2.ActivationResponse);
this.Neurons.Add(gene3);
}
}
foreach (IGene gene4 in other.Links.Genes)
{
NEATLinkGene gene5 = (NEATLinkGene) gene4;
NEATLinkGene gene6 = new NEATLinkGene((long) gene5.FromNeuronID, (long) gene5.ToNeuronID, gene5.Enabled, gene5.InnovationId, gene5.Weight, gene5.Recurrent);
this.Links.Add(gene6);
}
return;
Label_0182:
this.neuronsChromosome = new Chromosome();
this.linksChromosome = new Chromosome();
base.GA = other.GA;
base.Chromosomes.Add(this.neuronsChromosome);
if (0 != 0)
{
goto Label_002F;
}
base.Chromosomes.Add(this.linksChromosome);
base.GenomeID = other.GenomeID;
this.networkDepth = other.networkDepth;
base.Population = other.Population;
base.Score = other.Score;
if (0x7fffffff == 0)
{
goto Label_0017;
}
base.AdjustedScore = other.AdjustedScore;
if (0 == 0)
{
base.AmountToSpawn = other.AmountToSpawn;
goto Label_0017;
}
goto Label_0182;
}
public NEATPopulation(int inputCount, int outputCount, int populationSize)
: base(populationSize)
{
int num;
NEATGenome genome;
this._neatActivationFunction = new ActivationSigmoid();
this._outputActivationFunction = new ActivationLinear();
this.InputCount = inputCount;
goto Label_00D5;
Label_0010:
if (num >= populationSize)
{
NEATGenome genome2 = (NEATGenome) base.Genomes[0];
base.Innovations = new NEATInnovationList(this, genome2.Links, genome2.Neurons);
if ((((uint) outputCount) & 0) != 0)
{
goto Label_00D5;
}
if (((uint) num) <= uint.MaxValue)
{
return;
}
goto Label_009D;
}
Label_0086:
genome = new NEATGenome(base.AssignGenomeID(), inputCount, outputCount);
base.Add(genome);
num++;
goto Label_0010;
Label_009D:
throw new NeuralNetworkError("Population must have more than zero genomes.");
Label_00D5:
this.OutputCount = outputCount;
if ((-2147483648 != 0) && (populationSize != 0))
{
num = 0;
if ((((uint) num) - ((uint) populationSize)) <= uint.MaxValue)
{
goto Label_0010;
}
goto Label_0086;
}
goto Label_009D;
}
/// <summary>
/// Construct a genome by copying another.
/// </summary>
///
/// <param name="other">The other genome.</param>
public NEATGenome(NEATGenome other)
{
neuronsChromosome = new Chromosome();
linksChromosome = new Chromosome();
GA = other.GA;
Chromosomes.Add(neuronsChromosome);
Chromosomes.Add(linksChromosome);
GenomeID = other.GenomeID;
networkDepth = other.networkDepth;
Population = other.Population;
Score = other.Score;
AdjustedScore = other.AdjustedScore;
AmountToSpawn = other.AmountToSpawn;
inputCount = other.inputCount;
outputCount = other.outputCount;
speciesID = other.speciesID;
// copy neurons
foreach (IGene gene in other.Neurons.Genes)
{
var oldGene = (NEATNeuronGene)gene;
var newGene = new NEATNeuronGene(
oldGene.NeuronType, oldGene.Id,
oldGene.SplitY, oldGene.SplitX,
oldGene.Recurrent, oldGene.ActivationResponse);
Neurons.Add(newGene);
}
// copy links
foreach (IGene gene_0 in other.Links.Genes)
{
var oldGene_1 = (NEATLinkGene)gene_0;
var newGene_2 = new NEATLinkGene(
oldGene_1.FromNeuronID, oldGene_1.ToNeuronID,
oldGene_1.Enabled, oldGene_1.InnovationId,
oldGene_1.Weight, oldGene_1.Recurrent);
Links.Add(newGene_2);
}
}
/// <summary>
/// Construct a genome by copying another.
/// </summary>
///
/// <param name="other">The other genome.</param>
public NEATGenome(NEATGenome other)
{
neuronsChromosome = new Chromosome();
linksChromosome = new Chromosome();
GA = other.GA;
Chromosomes.Add(neuronsChromosome);
Chromosomes.Add(linksChromosome);
GenomeID = other.GenomeID;
networkDepth = other.networkDepth;
Population = other.Population;
Score = other.Score;
AdjustedScore = other.AdjustedScore;
AmountToSpawn = other.AmountToSpawn;
inputCount = other.inputCount;
outputCount = other.outputCount;
speciesID = other.speciesID;
// copy neurons
foreach (IGene gene in other.Neurons.Genes)
{
var oldGene = (NEATNeuronGene) gene;
var newGene = new NEATNeuronGene(
oldGene.NeuronType, oldGene.Id,
oldGene.SplitY, oldGene.SplitX,
oldGene.Recurrent, oldGene.ActivationResponse);
Neurons.Add(newGene);
}
// copy links
foreach (IGene gene_0 in other.Links.Genes)
{
var oldGene_1 = (NEATLinkGene) gene_0;
var newGene_2 = new NEATLinkGene(
oldGene_1.FromNeuronID, oldGene_1.ToNeuronID,
oldGene_1.Enabled, oldGene_1.InnovationId,
oldGene_1.Weight, oldGene_1.Recurrent);
Links.Add(newGene_2);
}
}
/// <summary>
/// Perform one training iteration.
/// </summary>
public override void Iteration()
{
iteration++;
IList<NEATGenome> newPop = new List<NEATGenome>();
int numSpawnedSoFar = 0;
foreach (ISpecies s in Population.Species)
{
if (numSpawnedSoFar < Population.Size())
{
var numToSpawn = (int) Math.Round(s.NumToSpawn);
bool bChosenBestYet = false;
while ((numToSpawn--) > 0)
{
NEATGenome baby = null;
if (!bChosenBestYet)
{
baby = (NEATGenome) s.Leader;
bChosenBestYet = true;
}
else
{
// if the number of individuals in this species is only
// one
// then we can only perform mutation
if (s.Members.Count == 1)
{
// spawn a child
baby = new NEATGenome((NEATGenome) s.ChooseParent());
}
else
{
var g1 = (NEATGenome) s.ChooseParent();
if (ThreadSafeRandom.NextDouble() < paramCrossoverRate)
{
var g2 = (NEATGenome) s.ChooseParent();
int numAttempts = 5;
while ((g1.GenomeID == g2.GenomeID)
&& ((numAttempts--) > 0))
{
g2 = (NEATGenome) s.ChooseParent();
}
if (g1.GenomeID != g2.GenomeID)
{
baby = Crossover(g1, g2);
}
}
else
{
baby = new NEATGenome(g1);
}
}
if (baby != null)
{
baby.GenomeID = Population.AssignGenomeID();
if (baby.Neurons.Size() < paramMaxPermittedNeurons)
{
baby.AddNeuron(paramChanceAddNode,
paramNumTrysToFindOldLink);
}
// now there's the chance a link may be added
baby.AddLink(paramChanceAddLink,
paramChanceAddRecurrentLink,
paramNumTrysToFindLoopedLink,
paramNumAddLinkAttempts);
// mutate the weights
baby.MutateWeights(paramMutationRate,
paramProbabilityWeightReplaced,
paramMaxWeightPerturbation);
baby.MutateActivationResponse(
paramActivationMutationRate,
paramMaxActivationPerturbation);
}
}
if (baby != null)
{
// sort the baby's genes by their innovation numbers
baby.SortGenes();
// add to new pop
// if (newPop.contains(baby)) {
// throw new EncogError("readd");
// }
newPop.Add(baby);
++numSpawnedSoFar;
if (numSpawnedSoFar == Population.Size())
{
numToSpawn = 0;
}
}
}
}
}
while (newPop.Count < Population.Size())
{
newPop.Add(TournamentSelection(Population.Size()/5));
}
Population.Clear();
foreach (NEATGenome genome in newPop)
{
Population.Add(genome);
}
ResetAndKill();
SortAndRecord();
SpeciateAndCalculateSpawnLevels();
}
/// <summary>
/// Perform a cross over.
/// </summary>
/// <param name="mom">The mother genome.</param>
/// <param name="dad">The father genome.</param>
/// <returns></returns>
public new NEATGenome Crossover(NEATGenome mom, NEATGenome dad)
{
NEATParent best;
// first determine who is more fit, the mother or the father?
if (mom.Score == dad.Score)
{
if (mom.NumGenes == dad.NumGenes)
{
if (ThreadSafeRandom.NextDouble() > 0)
{
best = NEATParent.Mom;
}
else
{
best = NEATParent.Dad;
}
}
else
{
if (mom.NumGenes < dad.NumGenes)
{
best = NEATParent.Mom;
}
else
{
best = NEATParent.Dad;
}
}
}
else
{
if (Comparator.IsBetterThan(mom.Score, dad.Score))
{
best = NEATParent.Mom;
}
else
{
best = NEATParent.Dad;
}
}
var babyNeurons = new Chromosome();
var babyGenes = new Chromosome();
var vecNeurons = new List<long>();
int curMom = 0;
int curDad = 0;
NEATLinkGene momGene;
NEATLinkGene dadGene;
NEATLinkGene selectedGene = null;
while ((curMom < mom.NumGenes) || (curDad < dad.NumGenes))
{
if (curMom < mom.NumGenes)
{
momGene = (NEATLinkGene) mom.Links.Get(curMom);
}
else
{
momGene = null;
}
if (curDad < dad.NumGenes)
{
dadGene = (NEATLinkGene) dad.Links.Get(curDad);
}
else
{
dadGene = null;
}
if ((momGene == null) && (dadGene != null))
{
if (best == NEATParent.Dad)
{
selectedGene = dadGene;
}
curDad++;
}
else if ((dadGene == null) && (momGene != null))
{
if (best == NEATParent.Mom)
{
selectedGene = momGene;
}
curMom++;
}
else if (momGene.InnovationId < dadGene.InnovationId)
{
if (best == NEATParent.Mom)
{
selectedGene = momGene;
}
curMom++;
}
else if (dadGene.InnovationId < momGene.InnovationId)
{
if (best == NEATParent.Dad)
{
selectedGene = dadGene;
}
curDad++;
}
else if (dadGene.InnovationId == momGene.InnovationId)
{
if (ThreadSafeRandom.NextDouble() < 0.5f)
{
selectedGene = momGene;
}
else
{
selectedGene = dadGene;
}
curMom++;
curDad++;
}
if (babyGenes.Size() == 0)
{
babyGenes.Add(selectedGene);
}
else
{
if (((NEATLinkGene) babyGenes.Get(babyGenes.Size() - 1))
.InnovationId != selectedGene.InnovationId)
{
babyGenes.Add(selectedGene);
}
}
// Check if we already have the nodes referred to in SelectedGene.
// If not, they need to be added.
AddNeuronID(selectedGene.FromNeuronID, vecNeurons);
AddNeuronID(selectedGene.ToNeuronID, vecNeurons);
} // end while
// now create the required nodes. First sort them into order
vecNeurons.Sort();
for (int i = 0; i < vecNeurons.Count; i++)
{
babyNeurons.Add(Innovations.CreateNeuronFromID(
vecNeurons[i]));
}
// finally, create the genome
var babyGenome = new NEATGenome(Population
.AssignGenomeID(), babyNeurons, babyGenes, mom.InputCount,
mom.OutputCount);
babyGenome.GA = this;
babyGenome.Population = Population;
return babyGenome;
}
/// <inheritdoc/>
public Object Read(Stream istream)
{
long nextInnovationId = 0;
long nextGeneId = 0;
var result = new NEATPopulation();
var innovationList = new NEATInnovationList {Population = result};
result.Innovations = innovationList;
var reader = new EncogReadHelper(istream);
EncogFileSection section;
while ((section = reader.ReadNextSection()) != null)
{
if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("INNOVATIONS"))
{
foreach (String line in section.Lines)
{
IList<String> cols = EncogFileSection
.SplitColumns(line);
var innovation = new NEATInnovation();
var innovationId = int.Parse(cols[1]);
innovation.InnovationId = innovationId;
innovation.NeuronId = int.Parse(cols[2]);
result.Innovations.Innovations[cols[0]] = innovation;
nextInnovationId = Math.Max(nextInnovationId, innovationId + 1);
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("SPECIES"))
{
NEATGenome lastGenome = null;
BasicSpecies lastSpecies = null;
foreach (String line in section.Lines)
{
IList<String> cols = EncogFileSection.SplitColumns(line);
if (String.Compare(cols[0], "s", StringComparison.OrdinalIgnoreCase) == 0)
{
lastSpecies = new BasicSpecies
{
Population = result,
Age = int.Parse(cols[1]),
BestScore = CSVFormat.EgFormat.Parse(cols[2]),
GensNoImprovement = int.Parse(cols[3])
};
result.Species.Add(lastSpecies);
}
else if (String.Compare(cols[0], "g", StringComparison.OrdinalIgnoreCase) == 0)
{
bool isLeader = lastGenome == null;
lastGenome = new NEATGenome
{
InputCount = result.InputCount,
OutputCount = result.OutputCount,
Species = lastSpecies,
AdjustedScore = CSVFormat.EgFormat.Parse(cols[1]),
Score = CSVFormat.EgFormat.Parse(cols[2]),
BirthGeneration = int.Parse(cols[3])
};
lastSpecies.Add(lastGenome);
if (isLeader)
{
lastSpecies.Leader = lastGenome;
}
}
else if (String.Compare(cols[0], "n", StringComparison.OrdinalIgnoreCase) == 0)
{
var neuronGene = new NEATNeuronGene();
int geneId = int.Parse(cols[1]);
neuronGene.Id = geneId;
IActivationFunction af = EncogFileSection.ParseActivationFunction(cols[2]);
neuronGene.ActivationFunction = af;
neuronGene.NeuronType = PersistNEATPopulation.StringToNeuronType(cols[3]);
neuronGene.InnovationId = int.Parse(cols[4]);
lastGenome.NeuronsChromosome.Add(neuronGene);
nextGeneId = Math.Max(geneId + 1, nextGeneId);
}
else if (String.Compare(cols[0], "l", StringComparison.OrdinalIgnoreCase) == 0)
{
var linkGene = new NEATLinkGene
{
Id = int.Parse(cols[1]),
Enabled = (int.Parse(cols[2]) > 0),
FromNeuronId = int.Parse(cols[3]),
ToNeuronId = int.Parse(cols[4]),
Weight = CSVFormat.EgFormat.Parse(cols[5]),
InnovationId = int.Parse(cols[6])
};
lastGenome.LinksChromosome.Add(linkGene);
}
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("CONFIG"))
{
IDictionary<string, string> prm = section.ParseParams();
string afStr = prm[NEATPopulation.PropertyNEATActivation];
if (String.Compare(afStr, TypeCppn, StringComparison.OrdinalIgnoreCase) == 0)
{
HyperNEATGenome.BuildCPPNActivationFunctions(result.ActivationFunctions);
}
else
{
result.NEATActivationFunction = EncogFileSection.ParseActivationFunction(prm,
NEATPopulation.PropertyNEATActivation);
}
result.ActivationCycles = EncogFileSection.ParseInt(prm,
PersistConst.ActivationCycles);
result.InputCount = EncogFileSection.ParseInt(prm,
PersistConst.InputCount);
result.OutputCount = EncogFileSection.ParseInt(prm,
PersistConst.OutputCount);
result.PopulationSize = EncogFileSection.ParseInt(prm,
NEATPopulation.PropertyPopulationSize);
result.SurvivalRate = EncogFileSection.ParseDouble(prm,
NEATPopulation.PropertySurvivalRate);
result.ActivationCycles = EncogFileSection.ParseInt(prm,
NEATPopulation.PropertyCycles);
}
}
// set factories
if (result.IsHyperNEAT)
{
result.GenomeFactory = new FactorHyperNEATGenome();
result.CODEC = new HyperNEATCODEC();
}
else
{
result.GenomeFactory = new FactorNEATGenome();
result.CODEC = new NEATCODEC();
}
// set the next ID's
result.InnovationIDGenerate.CurrentID = nextInnovationId;
result.GeneIdGenerate.CurrentID = nextGeneId;
// find first genome, which should be the best genome
if (result.Species.Count > 0)
{
ISpecies species = result.Species[0];
if (species.Members.Count > 0)
{
result.BestGenome = species.Members[0];
}
}
return result;
}
/// <summary>
/// Read the object.
/// </summary>
/// <param name="mask0">The stream to read the object from.</param>
/// <returns>The object that was loaded.</returns>
public virtual Object Read(Stream mask0)
{
var result = new NEATPopulation();
var innovationList = new NEATInnovationList {Population = result};
result.Innovations = innovationList;
var ins0 = new EncogReadHelper(mask0);
IDictionary<Int32, ISpecies> speciesMap = new Dictionary<Int32, ISpecies>();
IDictionary<ISpecies, Int32> leaderMap = new Dictionary<ISpecies, Int32>();
IDictionary<Int32, IGenome> genomeMap = new Dictionary<Int32, IGenome>();
EncogFileSection section;
while ((section = ins0.ReadNextSection()) != null)
{
if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("INNOVATIONS"))
{
foreach (String line in section.Lines)
{
IList<String> cols = EncogFileSection.SplitColumns(line);
var innovation = new NEATInnovation
{
InnovationID = Int32.Parse(cols[0]),
InnovationType = StringToInnovationType(cols[1]),
NeuronType = StringToNeuronType(cols[2]),
SplitX = CSVFormat.EgFormat.Parse(cols[3]),
SplitY = CSVFormat.EgFormat.Parse(cols[4]),
NeuronID = Int32.Parse(cols[5]),
FromNeuronID = Int32.Parse(cols[6]),
ToNeuronID = Int32.Parse(cols[7])
};
result.Innovations.Add(innovation);
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("SPECIES"))
{
foreach (String line in section.Lines)
{
String[] cols = line.Split(',');
var species = new BasicSpecies
{
SpeciesID = Int32.Parse(cols[0]),
Age = Int32.Parse(cols[1]),
BestScore = CSVFormat.EgFormat.Parse(cols[2]),
GensNoImprovement = Int32.Parse(cols[3]),
SpawnsRequired = CSVFormat.EgFormat
.Parse(cols[4])
};
species.SpawnsRequired = CSVFormat.EgFormat
.Parse(cols[5]);
leaderMap[(species)] = (Int32.Parse(cols[6]));
result.Species.Add(species);
speciesMap[((int) species.SpeciesID)] = (species);
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("GENOMES"))
{
NEATGenome lastGenome = null;
foreach (String line in section.Lines)
{
IList<String> cols = EncogFileSection.SplitColumns(line);
if (cols[0].Equals("g", StringComparison.InvariantCultureIgnoreCase))
{
lastGenome = new NEATGenome
{
NeuronsChromosome = new Chromosome(),
LinksChromosome = new Chromosome()
};
lastGenome.Chromosomes.Add(lastGenome.NeuronsChromosome);
lastGenome.Chromosomes.Add(lastGenome.LinksChromosome);
lastGenome.GenomeID = Int32.Parse(cols[1]);
lastGenome.SpeciesID = Int32.Parse(cols[2]);
lastGenome.AdjustedScore = CSVFormat.EgFormat
.Parse(cols[3]);
lastGenome.AmountToSpawn = CSVFormat.EgFormat
.Parse(cols[4]);
lastGenome.NetworkDepth = Int32.Parse(cols[5]);
lastGenome.Score = CSVFormat.EgFormat.Parse(cols[6]);
result.Add(lastGenome);
genomeMap[(int) lastGenome.GenomeID] = lastGenome;
}
else if (cols[0].Equals("n", StringComparison.InvariantCultureIgnoreCase))
{
var neuronGene = new NEATNeuronGene
{
Id = Int32.Parse(cols[1]),
NeuronType = StringToNeuronType(cols[2]),
Enabled = Int32.Parse(cols[3]) > 0,
InnovationId = Int32.Parse(cols[4]),
ActivationResponse = CSVFormat.EgFormat
.Parse(cols[5]),
SplitX = CSVFormat.EgFormat.Parse(cols[6]),
SplitY = CSVFormat.EgFormat.Parse(cols[7])
};
lastGenome.Neurons.Add(neuronGene);
}
else if (cols[0].Equals("l", StringComparison.InvariantCultureIgnoreCase))
{
var linkGene = new NEATLinkGene();
linkGene.Id = Int32.Parse(cols[1]);
linkGene.Enabled = Int32.Parse(cols[2]) > 0;
linkGene.Recurrent = Int32.Parse(cols[3]) > 0;
linkGene.FromNeuronID = Int32.Parse(cols[4]);
linkGene.ToNeuronID = Int32.Parse(cols[5]);
linkGene.Weight = CSVFormat.EgFormat.Parse(cols[6]);
linkGene.InnovationId = Int32.Parse(cols[7]);
lastGenome.Links.Add(linkGene);
}
}
}
else if (section.SectionName.Equals("NEAT-POPULATION")
&& section.SubSectionName.Equals("CONFIG"))
{
IDictionary<String, String> paras = section.ParseParams();
result.NeatActivationFunction = EncogFileSection
.ParseActivationFunction(paras,
NEATPopulation.PropertyNEATActivation);
result.OutputActivationFunction = EncogFileSection
.ParseActivationFunction(paras,
NEATPopulation.PropertyOutputActivation);
result.Snapshot = EncogFileSection.ParseBoolean(paras,
PersistConst.Snapshot);
result.InputCount = EncogFileSection.ParseInt(paras,
PersistConst.InputCount);
result.OutputCount = EncogFileSection.ParseInt(paras,
PersistConst.OutputCount);
result.OldAgePenalty = EncogFileSection.ParseDouble(paras,
PopulationConst.PropertyOldAgePenalty);
result.OldAgeThreshold = EncogFileSection.ParseInt(paras,
PopulationConst.PropertyOldAgeThreshold);
result.PopulationSize = EncogFileSection.ParseInt(paras,
PopulationConst.PropertyPopulationSize);
result.SurvivalRate = EncogFileSection.ParseDouble(paras,
PopulationConst.PropertySurvivalRate);
result.YoungBonusAgeThreshhold = EncogFileSection.ParseInt(
paras, PopulationConst.PropertyYoungAgeThreshold);
result.YoungScoreBonus = EncogFileSection.ParseDouble(paras,
PopulationConst.PropertyYoungAgeBonus);
result.GenomeIDGenerate.CurrentID = EncogFileSection.ParseInt(paras,
PopulationConst.
PropertyNextGenomeID);
result.InnovationIDGenerate.CurrentID = EncogFileSection.ParseInt(paras,
PopulationConst.
PropertyNextInnovationID);
result.GeneIDGenerate.CurrentID = EncogFileSection.ParseInt(paras,
PopulationConst.
PropertyNextGeneID);
result.SpeciesIDGenerate.CurrentID = EncogFileSection.ParseInt(paras,
PopulationConst.
PropertyNextSpeciesID);
}
}
// now link everything up
// first put all the genomes into correct species
foreach (IGenome genome in result.Genomes)
{
var neatGenome = (NEATGenome) genome;
var speciesId = (int) neatGenome.SpeciesID;
if( speciesMap.ContainsKey(speciesId))
{
ISpecies s = speciesMap[speciesId];
s.Members.Add(neatGenome);
}
neatGenome.InputCount = result.InputCount;
neatGenome.OutputCount = result.OutputCount;
}
// set the species leader links
foreach (ISpecies species in leaderMap.Keys)
{
int leaderID = leaderMap[species];
IGenome leader = genomeMap[leaderID];
species.Leader = leader;
((BasicSpecies) species).Population = result;
}
return result;
}
/// <summary>
/// Construct a starting NEAT population.
/// </summary>
///
/// <param name="inputCount">The input neuron count.</param>
/// <param name="outputCount">The output neuron count.</param>
/// <param name="populationSize">The population size.</param>
public NEATPopulation(int inputCount, int outputCount,
int populationSize)
: base(populationSize)
{
_neatActivationFunction = new ActivationSigmoid();
_outputActivationFunction = new ActivationLinear();
InputCount = inputCount;
OutputCount = outputCount;
if (populationSize == 0)
{
throw new NeuralNetworkError(
"Population must have more than zero genomes.");
}
// create the initial population
for (int i = 0; i < populationSize; i++)
{
var genome = new NEATGenome(AssignGenomeID(), inputCount,
outputCount);
Add(genome);
}
// create initial innovations
var genome2 = (NEATGenome) Genomes[0];
Innovations = new NEATInnovationList(this, genome2.Links,
genome2.Neurons);
}
/// <summary>
/// Perform one training iteration.
/// </summary>
public override void Iteration()
{
iteration++;
IList <NEATGenome> newPop = new List <NEATGenome>();
int numSpawnedSoFar = 0;
foreach (ISpecies s in Population.Species)
{
if (numSpawnedSoFar < Population.Size())
{
var numToSpawn = (int)Math.Round(s.NumToSpawn);
bool bChosenBestYet = false;
while ((numToSpawn--) > 0)
{
NEATGenome baby = null;
if (!bChosenBestYet)
{
baby = (NEATGenome)s.Leader;
bChosenBestYet = true;
}
else
{
// if the number of individuals in this species is only
// one
// then we can only perform mutation
if (s.Members.Count == 1)
{
// spawn a child
baby = new NEATGenome((NEATGenome)s.ChooseParent());
}
else
{
var g1 = (NEATGenome)s.ChooseParent();
if (ThreadSafeRandom.NextDouble() < paramCrossoverRate)
{
var g2 = (NEATGenome)s.ChooseParent();
int numAttempts = 5;
while ((g1.GenomeID == g2.GenomeID) &&
((numAttempts--) > 0))
{
g2 = (NEATGenome)s.ChooseParent();
}
if (g1.GenomeID != g2.GenomeID)
{
baby = Crossover(g1, g2);
}
}
else
{
baby = new NEATGenome(g1);
}
}
if (baby != null)
{
baby.GenomeID = Population.AssignGenomeID();
if (baby.Neurons.Size() < paramMaxPermittedNeurons)
{
baby.AddNeuron(paramChanceAddNode,
paramNumTrysToFindOldLink);
}
// now there's the chance a link may be added
baby.AddLink(paramChanceAddLink,
paramChanceAddRecurrentLink,
paramNumTrysToFindLoopedLink,
paramNumAddLinkAttempts);
// mutate the weights
baby.MutateWeights(paramMutationRate,
paramProbabilityWeightReplaced,
paramMaxWeightPerturbation);
baby.MutateActivationResponse(
paramActivationMutationRate,
paramMaxActivationPerturbation);
}
}
if (baby != null)
{
// sort the baby's genes by their innovation numbers
baby.SortGenes();
// add to new pop
// if (newPop.contains(baby)) {
// throw new EncogError("readd");
// }
newPop.Add(baby);
++numSpawnedSoFar;
if (numSpawnedSoFar == Population.Size())
{
numToSpawn = 0;
}
}
}
}
}
while (newPop.Count < Population.Size())
{
newPop.Add(TournamentSelection(Population.Size() / 5));
}
Population.Clear();
foreach (NEATGenome genome in newPop)
{
Population.Add(genome);
}
ResetAndKill();
SortAndRecord();
SpeciateAndCalculateSpawnLevels();
}
/// <summary>
/// Get the compatibility score with another genome. Used to determine
/// species.
/// </summary>
///
/// <param name="genome">The other genome.</param>
/// <returns>The score.</returns>
public double GetCompatibilityScore(NEATGenome genome)
{
double numDisjoint = 0;
double numExcess = 0;
double numMatched = 0;
double weightDifference = 0;
int g1 = 0;
int g2 = 0;
while ((g1 < linksChromosome.Size() - 1) ||
(g2 < linksChromosome.Size() - 1))
{
if (g1 == linksChromosome.Size() - 1)
{
g2++;
numExcess++;
continue;
}
if (g2 == genome.Links.Size() - 1)
{
g1++;
numExcess++;
continue;
}
// get innovation numbers for each gene at this point
long id1 = ((NEATLinkGene)linksChromosome.Get(g1)).InnovationId;
long id2 = ((NEATLinkGene)genome.Links.Get(g2)).InnovationId;
// innovation numbers are identical so increase the matched score
if (id1 == id2)
{
g1++;
g2++;
numMatched++;
// get the weight difference between these two genes
weightDifference += Math.Abs(((NEATLinkGene)linksChromosome.Get(g1)).Weight
- ((NEATLinkGene)genome.Links.Get(g2)).Weight);
}
// innovation numbers are different so increment the disjoint score
if (id1 < id2)
{
numDisjoint++;
g1++;
}
if (id1 > id2)
{
++numDisjoint;
++g2;
}
}
int longest = genome.NumGenes;
if (NumGenes > longest)
{
longest = NumGenes;
}
double score = (TWEAK_EXCESS * numExcess / longest)
+ (TWEAK_DISJOINT * numDisjoint / longest)
+ (TWEAK_MATCHED * weightDifference / numMatched);
return(score);
}
public double GetCompatibilityScore(NEATGenome genome)
{
double num2;
double num3;
double num4;
int num5;
int num6;
long num7;
long innovationId;
int numGenes;
double num10;
double num = 0.0;
goto Label_02B8;
Label_001B:
return ((((1.0 * num2) / ((double) numGenes)) + ((1.0 * num) / ((double) numGenes))) + ((0.4 * num4) / num3));
Label_005C:
if (num7 > innovationId)
{
num++;
goto Label_00BD;
}
Label_0062:
if ((num5 < (this.linksChromosome.Size() - 1)) || (num6 < (this.linksChromosome.Size() - 1)))
{
goto Label_0257;
}
numGenes = genome.NumGenes;
if ((((uint) num5) + ((uint) numGenes)) <= uint.MaxValue)
{
if (this.NumGenes > numGenes)
{
numGenes = this.NumGenes;
}
goto Label_001B;
}
Label_00BD:
num6++;
goto Label_0062;
Label_00C5:
num5++;
if ((((uint) num10) + ((uint) num7)) < 0)
{
goto Label_01D0;
}
goto Label_005C;
Label_00EB:
if (num7 < innovationId)
{
num++;
goto Label_00C5;
}
goto Label_005C;
Label_01D0:
num7 = ((NEATLinkGene) this.linksChromosome.Get(num5)).InnovationId;
innovationId = ((NEATLinkGene) genome.Links.Get(num6)).InnovationId;
if (num7 != innovationId)
{
goto Label_00EB;
}
if ((((uint) num4) - ((uint) num2)) <= uint.MaxValue)
{
if ((((uint) num6) | 2) != 0)
{
num5++;
if ((((uint) num10) + ((uint) innovationId)) > uint.MaxValue)
{
return num10;
}
if ((((uint) num2) | 15) != 0)
{
num6++;
if (0 != 0)
{
goto Label_001B;
}
num3++;
if ((((uint) num6) - ((uint) num)) <= uint.MaxValue)
{
num4 += Math.Abs((double) (((NEATLinkGene) this.linksChromosome.Get(num5)).Weight - ((NEATLinkGene) genome.Links.Get(num6)).Weight));
goto Label_00EB;
}
goto Label_00C5;
}
}
else
{
goto Label_02B8;
}
}
Label_0257:
while (num5 == (this.linksChromosome.Size() - 1))
{
num6++;
num2++;
goto Label_0062;
}
if (num6 == (genome.Links.Size() - 1))
{
num5++;
num2++;
goto Label_0062;
}
goto Label_01D0;
Label_02B8:
num2 = 0.0;
num3 = 0.0;
num4 = 0.0;
num5 = 0;
num6 = 0;
if ((((uint) innovationId) - ((uint) num3)) > uint.MaxValue)
{
goto Label_01D0;
}
goto Label_0062;
}
/// <summary>
/// Get the compatibility score with another genome. Used to determine
/// species.
/// </summary>
///
/// <param name="genome">The other genome.</param>
/// <returns>The score.</returns>
public double GetCompatibilityScore(NEATGenome genome)
{
double numDisjoint = 0;
double numExcess = 0;
double numMatched = 0;
double weightDifference = 0;
int g1 = 0;
int g2 = 0;
while ((g1 < linksChromosome.Size() - 1)
|| (g2 < linksChromosome.Size() - 1))
{
if (g1 == linksChromosome.Size() - 1)
{
g2++;
numExcess++;
continue;
}
if (g2 == genome.Links.Size() - 1)
{
g1++;
numExcess++;
continue;
}
// get innovation numbers for each gene at this point
long id1 = ((NEATLinkGene) linksChromosome.Get(g1)).InnovationId;
long id2 = ((NEATLinkGene) genome.Links.Get(g2)).InnovationId;
// innovation numbers are identical so increase the matched score
if (id1 == id2)
{
g1++;
g2++;
numMatched++;
// get the weight difference between these two genes
weightDifference += Math.Abs(((NEATLinkGene) linksChromosome.Get(g1)).Weight
- ((NEATLinkGene) genome.Links.Get(g2)).Weight);
}
// innovation numbers are different so increment the disjoint score
if (id1 < id2)
{
numDisjoint++;
g1++;
}
if (id1 > id2)
{
++numDisjoint;
++g2;
}
}
int longest = genome.NumGenes;
if (NumGenes > longest)
{
longest = NumGenes;
}
double score = (TWEAK_EXCESS*numExcess/longest)
+ (TWEAK_DISJOINT*numDisjoint/longest)
+ (TWEAK_MATCHED*weightDifference/numMatched);
return score;
}
public override void Iteration()
{
IList<NEATGenome> list;
int num;
int num2;
bool flag;
int num3;
this.x47b4ed2c32cb276e++;
goto Label_00D0;
Label_0024:
if (list.Count < base.Population.Size())
{
goto Label_04AD;
}
if ((((uint) num2) | 1) != 0)
{
base.Population.Clear();
}
foreach (NEATGenome genome4 in list)
{
base.Population.Add(genome4);
}
this.ResetAndKill();
if ((((uint) num) - ((uint) flag)) <= uint.MaxValue)
{
this.SortAndRecord();
this.SpeciateAndCalculateSpawnLevels();
}
if ((((uint) num2) - ((uint) num3)) >= 0)
{
return;
}
Label_00D0:
list = new List<NEATGenome>();
num = 0;
using (IEnumerator<ISpecies> enumerator = base.Population.Species.GetEnumerator())
{
ISpecies species;
NEATGenome genome;
NEATGenome genome2;
NEATGenome genome3;
goto Label_00FD;
Label_00EC:
if (num < base.Population.Size())
{
goto Label_0485;
}
Label_00FD:
if (enumerator.MoveNext())
{
goto Label_0468;
}
goto Label_040A;
Label_010D:
if (num == base.Population.Size())
{
goto Label_0144;
}
Label_011B:
if (num2-- > 0)
{
goto Label_0441;
}
goto Label_00FD;
Label_012C:
if (genome != null)
{
goto Label_0182;
}
if (((uint) num) >= 0)
{
goto Label_011B;
}
goto Label_040A;
Label_0144:
num2 = 0;
goto Label_011B;
Label_014D:
if (0 == 0)
{
goto Label_010D;
}
goto Label_01FA;
Label_0152:
if (0x7fffffff == 0)
{
goto Label_03D9;
}
if ((((uint) num2) & 0) != 0)
{
goto Label_0266;
}
num++;
goto Label_014D;
Label_0179:
if (genome != null)
{
goto Label_0246;
}
goto Label_012C;
Label_0182:
genome.SortGenes();
list.Add(genome);
goto Label_0152;
Label_0197:
genome.AddNeuron(this.xe6c7b0462e12d2ff, this.x340c2bbd00cd3fa4);
Label_01AA:
genome.AddLink(this.x67e8029e782709f0, this.xd3f94467320a5684, this.xe44426390f1f3741, this.xd7944ba63721a56b);
genome.MutateWeights(this.x68e0847485ce0c21, this.xe5ff50155887c0e7, this.x7a6edccccc229234);
genome.MutateActivationResponse(this.xd9d3bb742c7a307b, this.xf52a69d338e65c0f);
goto Label_012C;
Label_01FA:
if ((((uint) num3) - ((uint) num2)) >= 0)
{
goto Label_0144;
}
Label_0212:
if (genome.Neurons.Size() >= this.x214332e2bd2e8ae1)
{
goto Label_01AA;
}
goto Label_0197;
Label_0231:
if (genome2.GenomeID != genome3.GenomeID)
{
goto Label_0266;
}
goto Label_0179;
Label_0246:
genome.GenomeID = base.Population.AssignGenomeID();
goto Label_0212;
Label_0266:
genome = this.Crossover(genome2, genome3);
goto Label_0179;
Label_0277:
genome = new NEATGenome(genome2);
goto Label_0179;
Label_0285:
if ((((uint) flag) + ((uint) num)) < 0)
{
goto Label_0492;
}
Label_02A0:
if (genome2.GenomeID == genome3.GenomeID)
{
goto Label_0334;
}
if (((uint) num) >= 0)
{
goto Label_0231;
}
if ((((uint) num) + ((uint) num)) > uint.MaxValue)
{
goto Label_0197;
}
if ((((uint) num3) | 0xfffffffe) == 0)
{
goto Label_02A0;
}
Label_02FE:
if ((((uint) flag) & 0) != 0)
{
goto Label_02A0;
}
if ((((uint) flag) + ((uint) flag)) >= 0)
{
goto Label_0231;
}
goto Label_03F5;
Label_0334:
if (num3-- <= 0)
{
goto Label_02FE;
}
genome3 = (NEATGenome) species.ChooseParent();
if ((((uint) num) - ((uint) num2)) >= 0)
{
goto Label_03AA;
}
Label_036A:
if (species.Members.Count == 1)
{
goto Label_03D9;
}
genome2 = (NEATGenome) species.ChooseParent();
if (ThreadSafeRandom.NextDouble() >= this.xa4a074c49c97739c)
{
goto Label_0277;
}
genome3 = (NEATGenome) species.ChooseParent();
num3 = 5;
goto Label_02A0;
Label_03AA:
if ((((uint) num) - ((uint) flag)) >= 0)
{
goto Label_02A0;
}
Label_03C4:
genome = (NEATGenome) species.Leader;
flag = true;
goto Label_012C;
Label_03D9:
genome = new NEATGenome((NEATGenome) species.ChooseParent());
goto Label_0179;
Label_03F5:
if (((uint) num) >= 0)
{
goto Label_0231;
}
Label_040A:
if (((uint) num) >= 0)
{
goto Label_0024;
}
goto Label_044D;
Label_0421:
if ((((uint) num) - ((uint) flag)) > uint.MaxValue)
{
goto Label_0144;
}
goto Label_011B;
Label_0441:
genome = null;
if (flag)
{
goto Label_036A;
}
goto Label_03C4;
Label_044D:
if ((((uint) num3) - ((uint) flag)) > uint.MaxValue)
{
goto Label_0285;
}
Label_0468:
species = enumerator.Current;
if (((uint) num2) >= 0)
{
goto Label_00EC;
}
Label_0485:
num2 = (int) Math.Round(species.NumToSpawn);
Label_0492:
flag = false;
goto Label_0421;
}
Label_04AD:
list.Add(this.TournamentSelection(base.Population.Size() / 5));
goto Label_0024;
}
public NEATGenome Crossover(NEATGenome mom, NEATGenome dad)
{
x47361738465134f2 xf;
Chromosome chromosome;
Chromosome chromosome2;
List<long> list;
int num;
int num2;
NEATLinkGene gene;
NEATLinkGene gene2;
NEATLinkGene gene3;
int num3;
NEATGenome genome;
if (mom.Score != dad.Score)
{
while (base.Comparator.IsBetterThan(mom.Score, dad.Score))
{
xf = x47361738465134f2.x431cb293a9d996e8;
if (((uint) num3) >= 0)
{
if ((((uint) num3) & 0) == 0)
{
goto Label_03BA;
}
goto Label_0399;
}
if ((((uint) num) & 0) == 0)
{
goto Label_0478;
}
}
xf = x47361738465134f2.x86f3d3d96a9a0f93;
goto Label_03BA;
}
goto Label_0478;
Label_002E:
genome = new NEATGenome(base.Population.AssignGenomeID(), chromosome, chromosome2, mom.InputCount, mom.OutputCount);
genome.GA = this;
if (15 != 0)
{
if (0 != 0)
{
goto Label_031C;
}
genome.Population = base.Population;
if ((((uint) num3) & 0) == 0)
{
return genome;
}
goto Label_02C3;
}
goto Label_00B2;
Label_0071:
num3++;
Label_0077:
if (num3 < list.Count)
{
chromosome.Add(this.Innovations.CreateNeuronFromID(list[num3]));
goto Label_0071;
}
goto Label_002E;
Label_00B2:
this.AddNeuronID((long) gene3.FromNeuronID, list);
this.AddNeuronID((long) gene3.ToNeuronID, list);
Label_00D0:
if ((num < mom.NumGenes) || (num2 < dad.NumGenes))
{
if (num >= mom.NumGenes)
{
gene = null;
}
else
{
gene = (NEATLinkGene) mom.Links.Get(num);
}
goto Label_034F;
}
list.Sort();
num3 = 0;
if ((((uint) num2) + ((uint) num)) > uint.MaxValue)
{
goto Label_0071;
}
if (0 != 0)
{
goto Label_034F;
}
goto Label_0077;
Label_0160:
chromosome2.Add(gene3);
goto Label_00B2;
Label_016D:
if (chromosome2.Size() == 0)
{
goto Label_0160;
}
if ((0 != 0) || (((NEATLinkGene) chromosome2.Get(chromosome2.Size() - 1)).InnovationId != gene3.InnovationId))
{
chromosome2.Add(gene3);
}
goto Label_00B2;
Label_01C8:
num++;
if (((uint) num) <= uint.MaxValue)
{
if (((uint) num3) > uint.MaxValue)
{
goto Label_002E;
}
if ((((uint) num2) | 4) == 0)
{
goto Label_025D;
}
num2++;
goto Label_016D;
}
Label_01E0:
if ((((uint) num2) | 2) != 0)
{
if ((((uint) num3) + ((uint) num3)) <= uint.MaxValue)
{
goto Label_016D;
}
goto Label_0160;
}
if (-2147483648 != 0)
{
goto Label_0234;
}
if ((((uint) num) + ((uint) num3)) < 0)
{
goto Label_024D;
}
Label_0222:
while (ThreadSafeRandom.NextDouble() < 0.5)
{
gene3 = gene;
goto Label_01C8;
}
gene3 = gene2;
goto Label_01C8;
Label_0234:
gene3 = gene2;
Label_0238:
num2++;
goto Label_016D;
Label_024D:
if (gene.InnovationId < gene2.InnovationId)
{
if (xf == x47361738465134f2.x431cb293a9d996e8)
{
gene3 = gene;
}
num++;
goto Label_016D;
}
Label_025D:
if (gene2.InnovationId >= gene.InnovationId)
{
if (gene2.InnovationId == gene.InnovationId)
{
goto Label_0222;
}
goto Label_01E0;
}
if ((((uint) num2) + ((uint) num)) > uint.MaxValue)
{
goto Label_024D;
}
if (xf != x47361738465134f2.x86f3d3d96a9a0f93)
{
goto Label_0238;
}
goto Label_0234;
Label_02C3:
if (gene2 == null)
{
if (gene != null)
{
if (xf == x47361738465134f2.x431cb293a9d996e8)
{
gene3 = gene;
if ((((uint) num2) + ((uint) num)) > uint.MaxValue)
{
goto Label_03BA;
}
}
num++;
goto Label_016D;
}
if ((((uint) num3) | 0xfffffffe) != 0)
{
}
}
goto Label_024D;
Label_031C:
if (gene2 == null)
{
goto Label_02C3;
}
if (xf == x47361738465134f2.x86f3d3d96a9a0f93)
{
if (1 == 0)
{
goto Label_01C8;
}
gene3 = gene2;
}
num2++;
goto Label_016D;
Label_034F:
if (num2 < dad.NumGenes)
{
gene2 = (NEATLinkGene) dad.Links.Get(num2);
}
else
{
gene2 = null;
}
if (gene != null)
{
goto Label_02C3;
}
goto Label_031C;
Label_0399:
if ((((uint) num) & 0) != 0)
{
goto Label_00B2;
}
gene3 = null;
goto Label_00D0;
Label_03BA:
chromosome = new Chromosome();
chromosome2 = new Chromosome();
list = new List<long>();
num = 0;
num2 = 0;
if (0 == 0)
{
goto Label_0399;
}
Label_0478:
if (mom.NumGenes != dad.NumGenes)
{
if (mom.NumGenes < dad.NumGenes)
{
xf = x47361738465134f2.x431cb293a9d996e8;
}
else
{
xf = x47361738465134f2.x86f3d3d96a9a0f93;
}
}
else if (((((uint) num) - ((uint) num3)) >= 0) && (ThreadSafeRandom.NextDouble() <= 0.0))
{
if ((((uint) num3) + ((uint) num2)) <= uint.MaxValue)
{
xf = x47361738465134f2.x86f3d3d96a9a0f93;
}
}
else
{
xf = x47361738465134f2.x431cb293a9d996e8;
}
goto Label_03BA;
}
public virtual object Read(Stream mask0)
{
IDictionary<ISpecies, int> dictionary2;
IDictionary<int, IGenome> dictionary3;
EncogFileSection section;
IDictionary<string, string> dictionary4;
int num;
int num2;
NEATPopulation population = new NEATPopulation();
NEATInnovationList list = new NEATInnovationList {
Population = population
};
population.Innovations = list;
EncogReadHelper helper = new EncogReadHelper(mask0);
IDictionary<int, ISpecies> dictionary = new Dictionary<int, ISpecies>();
goto Label_0BD6;
Label_0023:
if ((section = helper.ReadNextSection()) != null)
{
if (!section.SectionName.Equals("NEAT-POPULATION"))
{
goto Label_085C;
}
if (section.SubSectionName.Equals("INNOVATIONS"))
{
using (IEnumerator<string> enumerator = section.Lines.GetEnumerator())
{
string str;
IList<string> list2;
NEATInnovation innovation;
NEATInnovation innovation2;
goto Label_0A6C;
Label_0A43:
innovation = innovation2;
if ((((uint) num2) - ((uint) num)) <= uint.MaxValue)
{
}
population.Innovations.Add(innovation);
Label_0A6C:
if (enumerator.MoveNext())
{
goto Label_0B54;
}
goto Label_0AD7;
Label_0A7A:
innovation2.SplitY = CSVFormat.EgFormat.Parse(list2[4]);
innovation2.NeuronID = int.Parse(list2[5]);
innovation2.FromNeuronID = int.Parse(list2[6]);
innovation2.ToNeuronID = int.Parse(list2[7]);
goto Label_0A43;
Label_0AD7:
if ((((uint) num2) - ((uint) num)) >= 0)
{
goto Label_0023;
}
Label_0AEF:
innovation2 = new NEATInnovation();
innovation2.InnovationID = int.Parse(list2[0]);
innovation2.InnovationType = StringToInnovationType(list2[1]);
innovation2.NeuronType = StringToNeuronType(list2[2]);
innovation2.SplitX = CSVFormat.EgFormat.Parse(list2[3]);
if (0 == 0)
{
goto Label_0A7A;
}
goto Label_0023;
Label_0B54:
str = enumerator.Current;
do
{
list2 = EncogFileSection.SplitColumns(str);
}
while (0 != 0);
goto Label_0AEF;
}
}
if (((uint) num) <= uint.MaxValue)
{
goto Label_085C;
}
goto Label_030B;
}
using (IEnumerator<IGenome> enumerator4 = population.Genomes.GetEnumerator())
{
IGenome genome3;
NEATGenome genome4;
ISpecies species3;
Label_0040:
if (enumerator4.MoveNext())
{
goto Label_00D6;
}
goto Label_0102;
Label_0051:
genome4.OutputCount = population.OutputCount;
if ((((uint) num) - ((uint) num2)) >= 0)
{
goto Label_0040;
}
Label_007D:
if (dictionary.ContainsKey(num))
{
goto Label_00BA;
}
Label_0087:
genome4.InputCount = population.InputCount;
goto Label_0051;
Label_0096:
num = (int) genome4.SpeciesID;
if ((((uint) num2) + ((uint) num2)) <= uint.MaxValue)
{
}
goto Label_007D;
Label_00BA:
species3 = dictionary[num];
species3.Members.Add(genome4);
goto Label_0087;
Label_00D6:
genome3 = enumerator4.Current;
genome4 = (NEATGenome) genome3;
goto Label_0096;
}
Label_0102:
using (IEnumerator<ISpecies> enumerator5 = dictionary2.Keys.GetEnumerator())
{
ISpecies current;
goto Label_011F;
Label_0112:
((BasicSpecies) current).Population = population;
Label_011F:
if (enumerator5.MoveNext())
{
current = enumerator5.Current;
num2 = dictionary2[current];
do
{
IGenome genome5 = dictionary3[num2];
current.Leader = genome5;
}
while (-1 == 0);
goto Label_0112;
}
return population;
}
Label_016E:
population.YoungScoreBonus = EncogFileSection.ParseDouble(dictionary4, "youngAgeBonus");
population.GenomeIDGenerate.CurrentID = EncogFileSection.ParseInt(dictionary4, "nextGenomeID");
population.InnovationIDGenerate.CurrentID = EncogFileSection.ParseInt(dictionary4, "nextInnovationID");
population.GeneIDGenerate.CurrentID = EncogFileSection.ParseInt(dictionary4, "nextGeneID");
population.SpeciesIDGenerate.CurrentID = EncogFileSection.ParseInt(dictionary4, "nextSpeciesID");
goto Label_0023;
Label_0201:
population.SurvivalRate = EncogFileSection.ParseDouble(dictionary4, "survivalRate");
if (0 != 0)
{
goto Label_03AA;
}
goto Label_02E9;
Label_0242:
population.OldAgePenalty = EncogFileSection.ParseDouble(dictionary4, "oldAgePenalty");
population.OldAgeThreshold = EncogFileSection.ParseInt(dictionary4, "oldAgeThreshold");
Label_0266:
population.PopulationSize = EncogFileSection.ParseInt(dictionary4, "populationSize");
if (((uint) num2) <= uint.MaxValue)
{
if ((((uint) num2) - ((uint) num2)) >= 0)
{
if ((((uint) num) + ((uint) num2)) > uint.MaxValue)
{
goto Label_0242;
}
goto Label_0201;
}
goto Label_02E9;
}
Label_028A:
population.OutputActivationFunction = EncogFileSection.ParseActivationFunction(dictionary4, "outAct");
if ((((uint) num2) + ((uint) num2)) < 0)
{
goto Label_0BD6;
}
population.Snapshot = EncogFileSection.ParseBoolean(dictionary4, "snapshot");
population.InputCount = EncogFileSection.ParseInt(dictionary4, "inputCount");
population.OutputCount = EncogFileSection.ParseInt(dictionary4, "outputCount");
goto Label_0242;
Label_02E9:
if ((((uint) num2) - ((uint) num)) >= 0)
{
population.YoungBonusAgeThreshhold = EncogFileSection.ParseInt(dictionary4, "youngAgeThreshold");
}
if (0xff != 0)
{
goto Label_016E;
}
Label_030B:
population.NeatActivationFunction = EncogFileSection.ParseActivationFunction(dictionary4, "neatAct");
goto Label_028A;
Label_03AA:
if (!section.SectionName.Equals("NEAT-POPULATION") || !section.SubSectionName.Equals("CONFIG"))
{
goto Label_0023;
}
if ((((uint) num2) + ((uint) num2)) <= uint.MaxValue)
{
if ((((uint) num2) + ((uint) num2)) <= uint.MaxValue)
{
dictionary4 = section.ParseParams();
}
goto Label_030B;
}
Label_0821:
if (section.SectionName.Equals("NEAT-POPULATION"))
{
if (section.SubSectionName.Equals("GENOMES"))
{
NEATGenome genome = null;
using (IEnumerator<string> enumerator3 = section.Lines.GetEnumerator())
{
string str3;
IList<string> list3;
NEATGenome genome2;
NEATNeuronGene gene;
NEATNeuronGene gene2;
NEATLinkGene gene3;
goto Label_0402;
Label_03DA:
genome.Links.Add(gene3);
goto Label_0402;
Label_03EA:
if (list3[0].Equals("l", StringComparison.InvariantCultureIgnoreCase))
{
goto Label_04EA;
}
Label_0402:
if (enumerator3.MoveNext())
{
goto Label_0770;
}
if ((((uint) num2) | 0x80000000) != 0)
{
goto Label_0023;
}
Label_0429:
gene3.Enabled = int.Parse(list3[2]) > 0;
Label_0440:
gene3.Recurrent = int.Parse(list3[3]) > 0;
gene3.FromNeuronID = int.Parse(list3[4]);
gene3.ToNeuronID = int.Parse(list3[5]);
gene3.Weight = CSVFormat.EgFormat.Parse(list3[6]);
gene3.InnovationId = int.Parse(list3[7]);
goto Label_03DA;
Label_04B4:
if ((((uint) num) & 0) != 0)
{
goto Label_03DA;
}
gene3.Id = int.Parse(list3[1]);
goto Label_0429;
Label_04EA:
gene3 = new NEATLinkGene();
goto Label_04B4;
Label_04F6:
gene2.SplitY = CSVFormat.EgFormat.Parse(list3[7]);
Label_050F:
gene = gene2;
genome.Neurons.Add(gene);
if ((((uint) num2) & 0) != 0)
{
goto Label_0782;
}
goto Label_0402;
Label_053D:
gene2.Enabled = int.Parse(list3[3]) > 0;
gene2.InnovationId = int.Parse(list3[4]);
if (0xff == 0)
{
goto Label_050F;
}
gene2.ActivationResponse = CSVFormat.EgFormat.Parse(list3[5]);
gene2.SplitX = CSVFormat.EgFormat.Parse(list3[6]);
goto Label_04F6;
Label_05A7:
gene2.Id = int.Parse(list3[1]);
gene2.NeuronType = StringToNeuronType(list3[2]);
goto Label_053D;
Label_05DA:
if (!list3[0].Equals("n", StringComparison.InvariantCultureIgnoreCase))
{
goto Label_03EA;
}
if (3 == 0)
{
goto Label_0440;
}
gene2 = new NEATNeuronGene();
goto Label_07C8;
Label_0608:
population.Add(genome);
dictionary3[(int) genome.GenomeID] = genome;
if (((uint) num) >= 0)
{
goto Label_0402;
}
goto Label_06B0;
Label_0638:
genome.AmountToSpawn = CSVFormat.EgFormat.Parse(list3[4]);
genome.NetworkDepth = int.Parse(list3[5]);
if ((((uint) num2) | 0x80000000) == 0)
{
goto Label_07AD;
}
if (((uint) num2) < 0)
{
goto Label_0023;
}
genome.Score = CSVFormat.EgFormat.Parse(list3[6]);
goto Label_06F8;
Label_06B0:
genome.GenomeID = int.Parse(list3[1]);
genome.SpeciesID = int.Parse(list3[2]);
genome.AdjustedScore = CSVFormat.EgFormat.Parse(list3[3]);
goto Label_0638;
Label_06F8:
if (3 != 0)
{
goto Label_0608;
}
goto Label_0402;
Label_0704:
genome.Chromosomes.Add(genome.LinksChromosome);
if ((((uint) num2) + ((uint) num2)) >= 0)
{
goto Label_06B0;
}
goto Label_0402;
Label_0737:
if (8 == 0)
{
goto Label_050F;
}
genome = genome2;
genome.Chromosomes.Add(genome.NeuronsChromosome);
if ((((uint) num) - ((uint) num2)) <= uint.MaxValue)
{
goto Label_0704;
}
Label_0770:
str3 = enumerator3.Current;
list3 = EncogFileSection.SplitColumns(str3);
Label_0782:
if (!list3[0].Equals("g", StringComparison.InvariantCultureIgnoreCase))
{
goto Label_05DA;
}
genome2 = new NEATGenome {
NeuronsChromosome = new Chromosome()
};
Label_07AD:
genome2.LinksChromosome = new Chromosome();
goto Label_0737;
Label_07C8:
if ((((uint) num2) - ((uint) num)) <= uint.MaxValue)
{
goto Label_05A7;
}
if (0 == 0)
{
goto Label_04EA;
}
goto Label_04B4;
}
}
if ((((uint) num2) < 0) || ((((uint) num2) - ((uint) num2)) > uint.MaxValue))
{
goto Label_030B;
}
}
goto Label_03AA;
Label_085C:
if (section.SectionName.Equals("NEAT-POPULATION"))
{
if ((((uint) num) | 1) == 0)
{
goto Label_0266;
}
if (section.SubSectionName.Equals("SPECIES"))
{
if ((((uint) num) | 8) == 0)
{
goto Label_0201;
}
using (IEnumerator<string> enumerator2 = section.Lines.GetEnumerator())
{
string str2;
string[] strArray;
BasicSpecies species;
BasicSpecies species2;
goto Label_0913;
Label_08CB:
species = species2;
species.SpawnsRequired = CSVFormat.EgFormat.Parse(strArray[5]);
dictionary2[species] = int.Parse(strArray[6]);
population.Species.Add(species);
dictionary[(int) species.SpeciesID] = species;
Label_0913:
if (enumerator2.MoveNext())
{
goto Label_09D6;
}
goto Label_0023;
Label_0924:
if ((((uint) num2) & 0) != 0)
{
goto Label_0969;
}
if (2 == 0)
{
goto Label_0924;
}
goto Label_09BE;
Label_0941:
species2 = new BasicSpecies();
species2.SpeciesID = int.Parse(strArray[0]);
species2.Age = int.Parse(strArray[1]);
Label_0969:
species2.BestScore = CSVFormat.EgFormat.Parse(strArray[2]);
species2.GensNoImprovement = int.Parse(strArray[3]);
species2.SpawnsRequired = CSVFormat.EgFormat.Parse(strArray[4]);
if ((((uint) num) + ((uint) num2)) >= 0)
{
goto Label_0924;
}
Label_09BE:
if ((((uint) num2) + ((uint) num)) <= uint.MaxValue)
{
goto Label_09FD;
}
Label_09D6:
str2 = enumerator2.Current;
strArray = str2.Split(new char[] { ',' });
goto Label_0941;
Label_09FD:
if ((((uint) num) - ((uint) num)) <= uint.MaxValue)
{
goto Label_08CB;
}
goto Label_0023;
}
}
}
goto Label_0821;
Label_0BD6:
dictionary2 = new Dictionary<ISpecies, int>();
dictionary3 = new Dictionary<int, IGenome>();
goto Label_0023;
}
/// <summary>
/// Perform a cross over.
/// </summary>
/// <param name="mom">The mother genome.</param>
/// <param name="dad">The father genome.</param>
/// <returns></returns>
public new NEATGenome Crossover(NEATGenome mom, NEATGenome dad)
{
NEATParent best;
// first determine who is more fit, the mother or the father?
if (mom.Score == dad.Score)
{
if (mom.NumGenes == dad.NumGenes)
{
if (ThreadSafeRandom.NextDouble() > 0)
{
best = NEATParent.Mom;
}
else
{
best = NEATParent.Dad;
}
}
else
{
if (mom.NumGenes < dad.NumGenes)
{
best = NEATParent.Mom;
}
else
{
best = NEATParent.Dad;
}
}
}
else
{
if (Comparator.IsBetterThan(mom.Score, dad.Score))
{
best = NEATParent.Mom;
}
else
{
best = NEATParent.Dad;
}
}
var babyNeurons = new Chromosome();
var babyGenes = new Chromosome();
var vecNeurons = new List <long>();
int curMom = 0;
int curDad = 0;
NEATLinkGene momGene;
NEATLinkGene dadGene;
NEATLinkGene selectedGene = null;
while ((curMom < mom.NumGenes) || (curDad < dad.NumGenes))
{
if (curMom < mom.NumGenes)
{
momGene = (NEATLinkGene)mom.Links.Get(curMom);
}
else
{
momGene = null;
}
if (curDad < dad.NumGenes)
{
dadGene = (NEATLinkGene)dad.Links.Get(curDad);
}
else
{
dadGene = null;
}
if ((momGene == null) && (dadGene != null))
{
if (best == NEATParent.Dad)
{
selectedGene = dadGene;
}
curDad++;
}
else if ((dadGene == null) && (momGene != null))
{
if (best == NEATParent.Mom)
{
selectedGene = momGene;
}
curMom++;
}
else if (momGene.InnovationId < dadGene.InnovationId)
{
if (best == NEATParent.Mom)
{
selectedGene = momGene;
}
curMom++;
}
else if (dadGene.InnovationId < momGene.InnovationId)
{
if (best == NEATParent.Dad)
{
selectedGene = dadGene;
}
curDad++;
}
else if (dadGene.InnovationId == momGene.InnovationId)
{
if (ThreadSafeRandom.NextDouble() < 0.5f)
{
selectedGene = momGene;
}
else
{
selectedGene = dadGene;
}
curMom++;
curDad++;
}
if (babyGenes.Size() == 0)
{
babyGenes.Add(selectedGene);
}
else
{
if (((NEATLinkGene)babyGenes.Get(babyGenes.Size() - 1))
.InnovationId != selectedGene.InnovationId)
{
babyGenes.Add(selectedGene);
}
}
// Check if we already have the nodes referred to in SelectedGene.
// If not, they need to be added.
AddNeuronID(selectedGene.FromNeuronID, vecNeurons);
AddNeuronID(selectedGene.ToNeuronID, vecNeurons);
} // end while
// now create the required nodes. First sort them into order
vecNeurons.Sort();
for (int i = 0; i < vecNeurons.Count; i++)
{
babyNeurons.Add(Innovations.CreateNeuronFromID(
vecNeurons[i]));
}
// finally, create the genome
var babyGenome = new NEATGenome(Population
.AssignGenomeID(), babyNeurons, babyGenes, mom.InputCount,
mom.OutputCount);
babyGenome.GA = this;
babyGenome.Population = Population;
return(babyGenome);
}
/// <inheritdoc/>
public object Clone()
{
var result = new NEATGenome();
result.Copy(this);
return result;
}
